-
Notifications
You must be signed in to change notification settings - Fork 5.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat(op_crates): webgpu #7977
feat(op_crates): webgpu #7977
Conversation
# Conflicts: # cli/worker.rs
I did some size comparisons with main branch: webgpu main Quite a bit larger. |
This is an epic feature that opens the door to doing serious scientific computing with JavaScript. We will likely be able to run TensorFlow.js on Deno without too much work after this. Having a dynamic runtime with easy GPU access is a game changer. @crowlKats and @lucacasonato have been working on this for months - it's hard to understate the effort that they have put in to deliver this branch. Thank you for your work on this!
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM :)
Huge thanks @crowlKats and @kvark! |
Closes #7863
missing:
create a webgpu instance with thenow handled at init and set in OpStateop_webgpu_create_instance
opop_webgpu_buffer_get_map_async
to workop_webgpu_buffer_get_mapped_range
be put into zero_copyMove TS types to unstable(do this in follow up)WPT tests(do this in follow up)[[device]]
internal slot to all objects except adapterCleanup automatically using FinalizationRegistry(do this in follow up)Examples can be found at https://github.com/crowlKats/webgpu-examples/